web-researcher

web-researcher is an agent for coding agents from arch3rPro/ark-space. It costs 29 tokens per session (316 once invoked), scanned A, original, MIT.

An AI role for collecting evidence from public websites, including search results, supplied URLs, site pages, structured data, and research sources.

In plain words
What is it for?
Use it to find sources, read URLs, map or crawl websites, extract structured information, research academic material, interact with pages, and set up monitors.
Why use it?
It routes different web tasks to suitable discovery, fetching, crawling, extraction, and monitoring methods instead of treating every web job the same.

Agent

Part of the ark-space plugin — 18 skills, 11 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/arch3rpro/ark-space/web-researcher
Clone the repo
git clone --depth 1 https://github.com/arch3rPro/ark-space

Or install ark-space, the plugin that ships this one along with the rest of its 18 skills, 11 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for web-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/arch3rpro/ark-space/web-researcher.svg)](https://agentmods.dev/agents/arch3rpro/ark-space/web-researcher)
Your own site
<a href="https://agentmods.dev/agents/arch3rpro/ark-space/web-researcher"><img src="https://agentmods.dev/badge/agents/arch3rpro/ark-space/web-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.00316
Opus 5 $0.00015 $0.00158
Sonnet 5 $0.00006 $0.00063
Haiku 4.5 $0.00003 $0.00032

Measured 5d ago against content hash 8a3b9a971ee4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-researcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

integrations/claude-code/agents/web-researcher.md · 26 lines

What it actually says

ArkSpace Web Researcher

You handle web search, source discovery, URL extraction, site mapping, crawling, structured extraction, browser interaction, monitors, and cited research synthesis.

Web Work

For web capability routing, follow workflows/web-capability-routing.md before provider selection.

Prefer arXiv for academic paper discovery, arXiv IDs, authors, categories, and preprint metadata. Prefer SearXNG for private or self-hosted search. Within the canonical skills, select Exa for semantic discovery, code context, and URL-seeded related pages; Tavily for broad current search and broad research synthesis; Firecrawl for rendering, structured extraction, crawling, interaction, and monitoring. Do not silently substitute a user-requested provider.

Decision Rules

  • Hand off to competitive-analyst when the user needs market, competitor, or product-evidence judgment rather than general research.
  • Hand off to knowledge-manager when the main task is organizing notes, editing Obsidian artifacts, or storing findings in Bases, Canvas, Kanban, or vault files.
  • Hand off to doc-writer when the main output is polished documentation rather than research evidence collection.
  • Stop and report when provider configuration is missing and the user declines setup or the host cannot safely collect the required secret.

Output

Return concise findings with source references when evidence matters.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 26 lines · 29 tokens per session scan A 8a3b9a971ee4

Subscribe to this mod's changes

web-researcher is an agent published in the GitHub repository arch3rPro/ark-space (2 stars, last pushed 9d ago), licensed MIT. It adds 29 tokens to every session and 316 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

ckm-scout

Use this agent when the user wants to search the openEHR Clinical Knowledge Manager (CKM) aggressively for reusable archetypes before authoring a new one. Enforces the reuse-first principle by running parallel searches with varied phrasings and returning a ranked reuse/specialize/new recommendation. Invoke proactively…

Cadasto/openehr-assistant-plugin · 411 tokens

spec-researcher

Use this agent when the user needs a grounded answer from openEHR specifications (Reference Model, Archetype Model, AQL, BASE, ITS-REST, LANG, CDS, etc.) that isn't already in an MCP guide digest. Uses the howto/spec-lookup methodology — llms.txt site index, Markdown twin URLs, and BMM-backed typespecificationget — to…

Cadasto/openehr-assistant-plugin · 382 tokens

clinical-modeler

Use this agent when the user needs to read, write, review, or edit local archetype (.adl), template (.oet, Archetype Designer .t.json, .opt), or composition files in the workspace. It writes only to the local workspace, and can perform read-only MCP lookups (terminology resolution, RM/AM type specs, guides, and…

Cadasto/openehr-assistant-plugin · 407 tokens

planner

Receives a requirement and produces a structured development plan with subtask decomposition.

zjio26/forge · 16 tokens

dev

Implements features based on a development plan, and fixes bugs reported by the test agent.

zjio26/forge · 19 tokens

learner

Learns from completed dev-test cycles and extracts reusable knowledge to avoid repeated pitfalls.

zjio26/forge · 18 tokens